Matching Items (6)
Filtering by
- Genre: Masters Thesis
Description
Large datasets of sub-meter aerial imagery represented as orthophoto mosaics are widely available today, and these data sets may hold a great deal of untapped information. This imagery has a potential to locate several types of features; for example, forests, parking lots, airports, residential areas, or freeways in the imagery. However, the appearances of these things vary based on many things including the time that the image is captured, the sensor settings, processing done to rectify the image, and the geographical and cultural context of the region captured by the image. This thesis explores the use of deep convolutional neural networks to classify land use from very high spatial resolution (VHR), orthorectified, visible band multispectral imagery. Recent technological and commercial applications have driven the collection a massive amount of VHR images in the visible red, green, blue (RGB) spectral bands, this work explores the potential for deep learning algorithms to exploit this imagery for automatic land use/ land cover (LULC) classification. The benefits of automatic visible band VHR LULC classifications may include applications such as automatic change detection or mapping. Recent work has shown the potential of Deep Learning approaches for land use classification; however, this thesis improves on the state-of-the-art by applying additional dataset augmenting approaches that are well suited for geospatial data. Furthermore, the generalizability of the classifiers is tested by extensively evaluating the classifiers on unseen datasets and we present the accuracy levels of the classifier in order to show that the results actually generalize beyond the small benchmarks used in training. Deep networks have many parameters, and therefore they are often built with very large sets of labeled data. Suitably large datasets for LULC are not easy to come by, but techniques such as refinement learning allow networks trained for one task to be retrained to perform another recognition task. Contributions of this thesis include demonstrating that deep networks trained for image recognition in one task (ImageNet) can be efficiently transferred to remote sensing applications and perform as well or better than manually crafted classifiers without requiring massive training data sets. This is demonstrated on the UC Merced dataset, where 96% mean accuracy is achieved using a CNN (Convolutional Neural Network) and 5-fold cross validation. These results are further tested on unrelated VHR images at the same resolution as the training set.
ContributorsUba, Nagesh Kumar (Author) / Femiani, John (Thesis advisor) / Razdan, Anshuman (Committee member) / Amresh, Ashish (Committee member) / Arizona State University (Publisher)
Created2016
Description
Context – Urbanization can have negative effects on bat habitat use through the loss and isolation of habitat even for volant bats. Yet, how bats respond to the changing landscape composition and configuration of urban environments remains poorly understood.
Objective – This study examines the relationship between bat habitat use and landscape pattern across multiple scales in the Phoenix metropolitan region. My research explores how landscape composition and configuration affects bat activity, foraging activity, and species richness (response variables), and the distinct habitats that they use.
Methods – I used a multi-scale landscape approach and acoustic monitoring data to create predictive models that identified the key predictor variables across multiple scales within the study area. I selected three scales with the intent of capturing the landscape, home range, and site scales, which may all be relevant for understanding bat habitat use.
Results – Overall, class-level metrics and configuration metrics best explained bat habitat use for bat species associated with this urban setting. The extent and extensiveness of water (corresponding to small water bodies and watercourses) were the most important predictor variables across all response variables. Bat activity was predicted to be high in native vegetation remnants, and low in native vegetation at the city periphery. Foraging activity was predicted to be high in fine-scale land cover heterogeneity. Species richness was predicted to be high in golf courses, and low in commercial areas. Bat habitat use was affected by urban landscape pattern mainly at the landscape and site scale.
Conclusions – My results suggested in hot arid urban landscapes water is a limiting factor for bats, even in urban landscapes where the availability of water may be greater than in outlying native desert habitat. Golf courses had the highest species richness, and included the detection of the uncommon pocketed free-tailed bat (Nyctinomops femorosaccus). Water cover types had the second highest species richness. Golf courses may serve as important stop-overs or refuges for rare or elusive bats. Urban waterways and golf courses are novel urban cover types that can serve as compliments to urban preserves, and other green spaces for bat conservation.
Objective – This study examines the relationship between bat habitat use and landscape pattern across multiple scales in the Phoenix metropolitan region. My research explores how landscape composition and configuration affects bat activity, foraging activity, and species richness (response variables), and the distinct habitats that they use.
Methods – I used a multi-scale landscape approach and acoustic monitoring data to create predictive models that identified the key predictor variables across multiple scales within the study area. I selected three scales with the intent of capturing the landscape, home range, and site scales, which may all be relevant for understanding bat habitat use.
Results – Overall, class-level metrics and configuration metrics best explained bat habitat use for bat species associated with this urban setting. The extent and extensiveness of water (corresponding to small water bodies and watercourses) were the most important predictor variables across all response variables. Bat activity was predicted to be high in native vegetation remnants, and low in native vegetation at the city periphery. Foraging activity was predicted to be high in fine-scale land cover heterogeneity. Species richness was predicted to be high in golf courses, and low in commercial areas. Bat habitat use was affected by urban landscape pattern mainly at the landscape and site scale.
Conclusions – My results suggested in hot arid urban landscapes water is a limiting factor for bats, even in urban landscapes where the availability of water may be greater than in outlying native desert habitat. Golf courses had the highest species richness, and included the detection of the uncommon pocketed free-tailed bat (Nyctinomops femorosaccus). Water cover types had the second highest species richness. Golf courses may serve as important stop-overs or refuges for rare or elusive bats. Urban waterways and golf courses are novel urban cover types that can serve as compliments to urban preserves, and other green spaces for bat conservation.
ContributorsBazelman, Tracy C (Author) / Wu, Jianguo (Thesis advisor) / Chambers, Carol L. (Thesis advisor) / Smith, Andrew T. (Committee member) / Arizona State University (Publisher)
Created2016
Description
This thesis investigates how homeless men and women who use one of only six human services campuses (hscs) in the nation negotiate the stigmatization they may feel as homeless people living in Phoenix, Arizona. An hsc centralizes services to one area of the city to decrease the run around of scattered-site service delivery. It also creates a legitimized space for the homeless in the city. A place for the homeless can be a rarity in cities like Phoenix that have a history of implementing revanchist policies and neo-liberal land use planning, most notably found in its downtown revitalization efforts. During Phoenix's development as a major metropolitan area, the homeless population emerged and lived a life on the margins until the 2005 creation of the Human Services Campus. This research unearths the experiences of homeless men and women who use the HSC today. I used qualitative methods, including document review, 14 in-depth interviews with homeless men and women, 7 interviews with service providers, informal conversations with additional homeless clients, and 14 months of field observations at the HSC to collect the data presented in this thesis. The results of this research illustrate reasons why the homeless clients interviewed were sensitive to the stigmatization of their social status, and how they managed their stigmatization through relationships with homeless peers and staff on the HSC. The presence of an action plan to exit homelessness was critical to the nature of these relationships for clients, because it influenced how clients perceived their own stigmatization as a homeless person.
ContributorsDe La Rosa Aceves, Aurelia Marie (Author) / Bolin, Bob (Thesis advisor) / Menjivar, Cecilia (Committee member) / Yabiku, Scott (Committee member) / Arizona State University (Publisher)
Created2011
Description
The United States has a long history of providing public parks and amenities, especially for children. Unfortunately, children today are spending less time in public parks, less time getting physical activity and more time being indoors and sedentary. While multiple factors may be responsible for this lack of activity, multiple researchers have found the availability of parks is a significant influence on the physical activity levels of children as well as on the occurrence of obesity related illness. Public parks are ideal locations for children to get physical activity, however they are not always equitably distributed within communities. Income and race/ethnicity especially are common variables found to impact availability of parks. Such socioeconomic variables typically have an impact on the availability of public parks within a community. Such variables may also impact the quality of the parks provided. A case study of Scottsdale, Arizona was conducted analyzing the availability of public parks within the City between the years of 1990 and 2000 and the current quality of the parks. Statistical analysis and observation were utilized to assess the amount of park space available (in acres) and the quality of the parks in comparison to selected socioeconomic variables including ethnicity, income and total percent housing type (single family or multi-family). All analysis was conducted using U.S. Census data from the years 1990 and 2000 and was at the tract level. The results of the analysis indicate that in contrast to the initial hypothesis and past research, within the City of Scottsdale, lower income neighborhoods actually have more public park space available to them than higher income neighborhoods. Between 1990 and 2000 the difference in park space between the lowest and highest income quartiles increased considerably, approximately 230% over the ten years. The quality analysis results indicate that the overall quality of parks is slightly higher in the highest income neighborhoods, which also have no parks that could be considered of poor quality. Given the atypical results of this analysis, further research is necessary to better understand the impacts of socioeconomic characteristics on park, especially regarding children.
ContributorsSamples, Samantha (Author) / Crewe, Katherine (Thesis advisor) / Booze, Randy (Committee member) / Pijawka, David (Committee member) / Arizona State University (Publisher)
Created2011
Description
Despite public demand for climate change mitigation and natural open space conservancy, existing political and design efforts are only beginning to address the declining efficacy of the biotic carbon pool (C-pool) to sequester carbon. Advances in understanding of biogeochemical processes have provided methods for estimating carbon embodied in natural open spaces and enhancing carbon sequestration efficacy. In this study, the benefits of carbon embodied in dryland open spaces are determined by estimating carbon flux and analyzing ecological, social, and economic benefits provided by sequestered carbon. Understanding the ecological processes and derived benefits of carbon exchange in dryland open spaces will provide insight into enhancing carbon sequestration efficacy. Open space carbon is estimated by calculating the amount of carbon sequestration (estimated in Mg C / ha / y) in dryland open space C-pools. Carbon sequestration in dryland open spaces can be summarized in five open space typologies: hydric, mesic, aridic, biomass for energy agriculture, and traditional agriculture. Hydric (wetland) systems receive a significant amount of moisture; mesic (riparian) systems receive a moderate amount of moisture; and aridic (dry) systems receive low amounts of moisture. Biomass for energy production (perennial biomass) and traditional agriculture (annual / traditional biomass) can be more effective carbon sinks if managed appropriately. Impacts of design interventions to the carbon capacity of dryland open space systems are calculated by estimating carbon exchange in existing open space (base case) compared to projections of carbon sequestered in a modified system (prototype design). A demonstration project at the Lower San Pedro River Watershed highlights the potential for enhancing carbon sequestration. The site-scale demonstration project takes into account a number of limiting factors and opportunities including: availability of water and ability to manipulate its course, existing and potential vegetation, soil types and use of carbon additives, and land-use (particularly agriculture). Specific design challenges to overcome included: restoring perennial water to the Lower San Pedro River, reestablishing hydric and mesic systems, linking fragmented vegetation, and establishing agricultural systems that provide economic opportunities and act as carbon sinks. The prototype design showed enhancing carbon sequestration efficacy by 128-133% is possible with conservative design interventions.
ContributorsHuck, Erick (Author) / Cook, Edward (Thesis advisor) / Green, Douglas (Committee member) / Brooks, Kenneth (Committee member) / Montemayor, Gabriel (Committee member) / Arizona State University (Publisher)
Created2012
Description
Global climate change, rising average temperatures, rising water levels, irregularities in climate and river regimes, and increasing anthropogenic disturbances pose a significant risk to the ecosystems of protected areas. Given that past conditions are different from future conditions, managing protected areas faces serious challenges. New management approaches and strategies are needed to overcome these challenges. Planners and academicians have established methodologies for assessing the quality of climate change adaptation and resilience plans. However, a similar plan quality evaluation that considers climate change adaptation for National Park General Management Plans has not been conducted. This study adapted that methodology for national park management plans and applied it to analyze National Park General Management Plans across nine United States climate regions. Furthermore, this thesis aims to address this gap by asking and answering the following question: How do existing management plans for national parks meet the principles identified for effective planning for climate change? In this study, national park management plans are evaluated according to 112 criteria across seven principles, allowing for direct comparison and conclusions on strengths and weaknesses. The study revealed the strengths and weaknesses of the plans. Plans generally have similar weak points and strong points. While some aspects, such as public participation and coordination, perform relatively well, there are critical shortcomings in articulating a vision for climate adaptation, addressing uncertainty, and developing detailed strategies and monitoring mechanisms. The study will contribute to a better understanding of how protected areas can prepare for climate change impacts.
ContributorsSeki, Muhammet Ali (Author) / Meerow, Sara (Thesis advisor) / King, David (Committee member) / Larson, Kelli (Committee member) / Arizona State University (Publisher)
Created2023